FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138261736> ?p ?o ?g. }

• W3138261736 endingPage "6933" @default.
• W3138261736 startingPage "6922" @default.
• W3138261736 abstract "In recent years, the number of traffic accident deaths due to distracted driving has been increasing dramatically. Fortunately, distracted driving can be detected by the rapidly developing deep learning technology. Nevertheless, considering that real-time detection is necessary, three contradictory requirements for an optimized network must be addressed: a small number of parameters, high accuracy, and high speed. We propose a new D-HCNN model based on a decreasing filter size with only 0.76M parameters, a much smaller number of parameters than that used by models in many other studies. D-HCNN uses HOG feature images, L2 weight regularization, dropout and batch normalization to improve the performance. We discuss the advantages and principles of D-HCNN in detail and conduct experimental evaluations on two public datasets, AUC Distracted Driver (AUCD2) and State Farm Distracted Driver Detection (SFD3). The accuracy on AUCD2 and SFD3 is 95.59% and 99.87%, respectively, higher than the accuracy achieved by many other state-of-the-art methods." @default.
• W3138261736 created "2021-03-29" @default.
• W3138261736 creator A5003076238 @default.
• W3138261736 creator A5004828717 @default.
• W3138261736 creator A5030910124 @default.
• W3138261736 creator A5065761129 @default.
• W3138261736 creator A5077542599 @default.
• W3138261736 date "2022-07-01" @default.
• W3138261736 modified "2023-10-16" @default.
• W3138261736 title "Distracted Driver Detection Based on a CNN With Decreasing Filter Size" @default.
• W3138261736 cites W1954390275 @default.
• W3138261736 cites W2070906768 @default.
• W3138261736 cites W2097117768 @default.
• W3138261736 cites W2137056506 @default.
• W3138261736 cites W2194775991 @default.
• W3138261736 cites W2324736398 @default.
• W3138261736 cites W2343672207 @default.
• W3138261736 cites W2617632090 @default.
• W3138261736 cites W2733839197 @default.
• W3138261736 cites W2743351574 @default.
• W3138261736 cites W2783719297 @default.
• W3138261736 cites W2890157139 @default.
• W3138261736 cites W2895866857 @default.
• W3138261736 cites W2902761076 @default.
• W3138261736 cites W2921864169 @default.
• W3138261736 cites W2964081807 @default.
• W3138261736 cites W2964350391 @default.
• W3138261736 cites W2995601699 @default.
• W3138261736 cites W3008111068 @default.
• W3138261736 cites W3010783597 @default.
• W3138261736 cites W3026578319 @default.
• W3138261736 cites W3028505546 @default.
• W3138261736 cites W3035542613 @default.
• W3138261736 cites W3092544652 @default.
• W3138261736 cites W3100763996 @default.
• W3138261736 cites W4248352566 @default.
• W3138261736 doi "https://doi.org/10.1109/tits.2021.3063521" @default.
• W3138261736 hasPublicationYear "2022" @default.
• W3138261736 type Work @default.
• W3138261736 sameAs 3138261736 @default.
• W3138261736 citedByCount "17" @default.
• W3138261736 countsByYear W31382617362021 @default.
• W3138261736 countsByYear W31382617362022 @default.
• W3138261736 countsByYear W31382617362023 @default.
• W3138261736 crossrefType "journal-article" @default.
• W3138261736 hasAuthorship W3138261736A5003076238 @default.
• W3138261736 hasAuthorship W3138261736A5004828717 @default.
• W3138261736 hasAuthorship W3138261736A5030910124 @default.
• W3138261736 hasAuthorship W3138261736A5065761129 @default.
• W3138261736 hasAuthorship W3138261736A5077542599 @default.
• W3138261736 hasConcept C108583219 @default.
• W3138261736 hasConcept C119857082 @default.
• W3138261736 hasConcept C136886441 @default.
• W3138261736 hasConcept C138885662 @default.
• W3138261736 hasConcept C144024400 @default.
• W3138261736 hasConcept C153180895 @default.
• W3138261736 hasConcept C154945302 @default.
• W3138261736 hasConcept C19165224 @default.
• W3138261736 hasConcept C2776135515 @default.
• W3138261736 hasConcept C2776145597 @default.
• W3138261736 hasConcept C2776401178 @default.
• W3138261736 hasConcept C2776465824 @default.
• W3138261736 hasConcept C3017944768 @default.
• W3138261736 hasConcept C41008148 @default.
• W3138261736 hasConcept C41895202 @default.
• W3138261736 hasConcept C50644808 @default.
• W3138261736 hasConcept C52622490 @default.
• W3138261736 hasConcept C71924100 @default.
• W3138261736 hasConcept C87833898 @default.
• W3138261736 hasConcept C99454951 @default.
• W3138261736 hasConceptScore W3138261736C108583219 @default.
• W3138261736 hasConceptScore W3138261736C119857082 @default.
• W3138261736 hasConceptScore W3138261736C136886441 @default.
• W3138261736 hasConceptScore W3138261736C138885662 @default.
• W3138261736 hasConceptScore W3138261736C144024400 @default.
• W3138261736 hasConceptScore W3138261736C153180895 @default.
• W3138261736 hasConceptScore W3138261736C154945302 @default.
• W3138261736 hasConceptScore W3138261736C19165224 @default.
• W3138261736 hasConceptScore W3138261736C2776135515 @default.
• W3138261736 hasConceptScore W3138261736C2776145597 @default.
• W3138261736 hasConceptScore W3138261736C2776401178 @default.
• W3138261736 hasConceptScore W3138261736C2776465824 @default.
• W3138261736 hasConceptScore W3138261736C3017944768 @default.
• W3138261736 hasConceptScore W3138261736C41008148 @default.
• W3138261736 hasConceptScore W3138261736C41895202 @default.
• W3138261736 hasConceptScore W3138261736C50644808 @default.
• W3138261736 hasConceptScore W3138261736C52622490 @default.
• W3138261736 hasConceptScore W3138261736C71924100 @default.
• W3138261736 hasConceptScore W3138261736C87833898 @default.
• W3138261736 hasConceptScore W3138261736C99454951 @default.
• W3138261736 hasFunder F4320321001 @default.
• W3138261736 hasFunder F4320337015 @default.
• W3138261736 hasIssue "7" @default.
• W3138261736 hasLocation W31382617361 @default.
• W3138261736 hasOpenAccess W3138261736 @default.
• W3138261736 hasPrimaryLocation W31382617361 @default.
• W3138261736 hasRelatedWork W2140205990 @default.
• W3138261736 hasRelatedWork W2546942002 @default.

• next